7 use bytes (); # for $bytes::hint_bits
10 # Icky 3.2 names with parentheses.
11 'LINE FEED' => 0x0A, # LINE FEED (LF)
12 'FORM FEED' => 0x0C, # FORM FEED (FF)
13 'CARRIAGE RETURN' => 0x0D, # CARRIAGE RETURN (CR)
14 'NEXT LINE' => 0x85, # NEXT LINE (NEL)
16 # Some variant names from Wikipedia
17 'SINGLE-SHIFT 2' => 0x8E,
18 'SINGLE-SHIFT 3' => 0x8F,
19 'PRIVATE USE 1' => 0x91,
20 'PRIVATE USE 2' => 0x92,
21 'START OF PROTECTED AREA' => 0x96,
22 'END OF PROTECTED AREA' => 0x97,
24 # Convenience. Standard abbreviations for the controls
26 'SOH' => 0x01, # START OF HEADING
27 'STX' => 0x02, # START OF TEXT
28 'ETX' => 0x03, # END OF TEXT
29 'EOT' => 0x04, # END OF TRANSMISSION
30 'ENQ' => 0x05, # ENQUIRY
31 'ACK' => 0x06, # ACKNOWLEDGE
33 'BS' => 0x08, # BACKSPACE
34 'HT' => 0x09, # HORIZONTAL TABULATION
35 'LF' => 0x0A, # LINE FEED (LF)
36 'VT' => 0x0B, # VERTICAL TABULATION
37 'FF' => 0x0C, # FORM FEED (FF)
38 'CR' => 0x0D, # CARRIAGE RETURN (CR)
39 'SO' => 0x0E, # SHIFT OUT
40 'SI' => 0x0F, # SHIFT IN
41 'DLE' => 0x10, # DATA LINK ESCAPE
42 'DC1' => 0x11, # DEVICE CONTROL ONE
43 'DC2' => 0x12, # DEVICE CONTROL TWO
44 'DC3' => 0x13, # DEVICE CONTROL THREE
45 'DC4' => 0x14, # DEVICE CONTROL FOUR
46 'NAK' => 0x15, # NEGATIVE ACKNOWLEDGE
47 'SYN' => 0x16, # SYNCHRONOUS IDLE
48 'ETB' => 0x17, # END OF TRANSMISSION BLOCK
49 'CAN' => 0x18, # CANCEL
50 'EOM' => 0x19, # END OF MEDIUM
51 'SUB' => 0x1A, # SUBSTITUTE
52 'ESC' => 0x1B, # ESCAPE
53 'FS' => 0x1C, # FILE SEPARATOR
54 'GS' => 0x1D, # GROUP SEPARATOR
55 'RS' => 0x1E, # RECORD SEPARATOR
56 'US' => 0x1F, # UNIT SEPARATOR
57 'DEL' => 0x7F, # DELETE
58 'BPH' => 0x82, # BREAK PERMITTED HERE
59 'NBH' => 0x83, # NO BREAK HERE
60 'NEL' => 0x85, # NEXT LINE (NEL)
61 'SSA' => 0x86, # START OF SELECTED AREA
62 'ESA' => 0x87, # END OF SELECTED AREA
63 'HTS' => 0x88, # CHARACTER TABULATION SET
64 'HTJ' => 0x89, # CHARACTER TABULATION WITH JUSTIFICATION
65 'VTS' => 0x8A, # LINE TABULATION SET
66 'PLD' => 0x8B, # PARTIAL LINE FORWARD
67 'PLU' => 0x8C, # PARTIAL LINE BACKWARD
68 'RI ' => 0x8D, # REVERSE LINE FEED
69 'SS2' => 0x8E, # SINGLE SHIFT TWO
70 'SS3' => 0x8F, # SINGLE SHIFT THREE
71 'DCS' => 0x90, # DEVICE CONTROL STRING
72 'PU1' => 0x91, # PRIVATE USE ONE
73 'PU2' => 0x92, # PRIVATE USE TWO
74 'STS' => 0x93, # SET TRANSMIT STATE
75 'CCH' => 0x94, # CANCEL CHARACTER
76 'MW ' => 0x95, # MESSAGE WAITING
77 'SPA' => 0x96, # START OF GUARDED AREA
78 'EPA' => 0x97, # END OF GUARDED AREA
79 'SOS' => 0x98, # START OF STRING
80 'SCI' => 0x9A, # SINGLE CHARACTER INTRODUCER
81 'CSI' => 0x9B, # CONTROL SEQUENCE INTRODUCER
82 'ST ' => 0x9C, # STRING TERMINATOR
83 'OSC' => 0x9D, # OPERATING SYSTEM COMMAND
84 'PM ' => 0x9E, # PRIVACY MESSAGE
85 'APC' => 0x9F, # APPLICATION PROGRAM COMMAND
87 # There are no names for these in the Unicode standard;
88 # perhaps should be deprecated, but then again there are
89 # no alternative names, so am not deprecating. And if
90 # did, the code would have to change to not recommend an
91 # alternative for these.
92 'PADDING CHARACTER' => 0x80,
94 'HIGH OCTET PRESET' => 0x81,
98 'SINGLE GRAPHIC CHARACTER INTRODUCER' => 0x99,
101 # More convenience. For further convenience,
102 # it is suggested some way of using the NamesList
103 # aliases be implemented, but there are ambiguities in
105 'BOM' => 0xFEFF, # BYTE ORDER MARK
106 'BYTE ORDER MARK'=> 0xFEFF,
107 'CGJ' => 0x034F, # COMBINING GRAPHEME JOINER
108 'FVS1' => 0x180B, # MONGOLIAN FREE VARIATION SELECTOR ONE
109 'FVS2' => 0x180C, # MONGOLIAN FREE VARIATION SELECTOR TWO
110 'FVS3' => 0x180D, # MONGOLIAN FREE VARIATION SELECTOR THREE
111 'LRE' => 0x202A, # LEFT-TO-RIGHT EMBEDDING
112 'LRM' => 0x200E, # LEFT-TO-RIGHT MARK
113 'LRO' => 0x202D, # LEFT-TO-RIGHT OVERRIDE
114 'MMSP' => 0x205F, # MEDIUM MATHEMATICAL SPACE
115 'MVS' => 0x180E, # MONGOLIAN VOWEL SEPARATOR
116 'NBSP' => 0x00A0, # NO-BREAK SPACE
117 'NNBSP' => 0x202F, # NARROW NO-BREAK SPACE
118 'PDF' => 0x202C, # POP DIRECTIONAL FORMATTING
119 'RLE' => 0x202B, # RIGHT-TO-LEFT EMBEDDING
120 'RLM' => 0x200F, # RIGHT-TO-LEFT MARK
121 'RLO' => 0x202E, # RIGHT-TO-LEFT OVERRIDE
122 'SHY' => 0x00AD, # SOFT HYPHEN
123 'VS1' => 0xFE00, # VARIATION SELECTOR-1
124 'VS2' => 0xFE01, # VARIATION SELECTOR-2
125 'VS3' => 0xFE02, # VARIATION SELECTOR-3
126 'VS4' => 0xFE03, # VARIATION SELECTOR-4
127 'VS5' => 0xFE04, # VARIATION SELECTOR-5
128 'VS6' => 0xFE05, # VARIATION SELECTOR-6
129 'VS7' => 0xFE06, # VARIATION SELECTOR-7
130 'VS8' => 0xFE07, # VARIATION SELECTOR-8
131 'VS9' => 0xFE08, # VARIATION SELECTOR-9
132 'VS10' => 0xFE09, # VARIATION SELECTOR-10
133 'VS11' => 0xFE0A, # VARIATION SELECTOR-11
134 'VS12' => 0xFE0B, # VARIATION SELECTOR-12
135 'VS13' => 0xFE0C, # VARIATION SELECTOR-13
136 'VS14' => 0xFE0D, # VARIATION SELECTOR-14
137 'VS15' => 0xFE0E, # VARIATION SELECTOR-15
138 'VS16' => 0xFE0F, # VARIATION SELECTOR-16
139 'VS17' => 0xE0100, # VARIATION SELECTOR-17
140 'VS18' => 0xE0101, # VARIATION SELECTOR-18
141 'VS19' => 0xE0102, # VARIATION SELECTOR-19
142 'VS20' => 0xE0103, # VARIATION SELECTOR-20
143 'VS21' => 0xE0104, # VARIATION SELECTOR-21
144 'VS22' => 0xE0105, # VARIATION SELECTOR-22
145 'VS23' => 0xE0106, # VARIATION SELECTOR-23
146 'VS24' => 0xE0107, # VARIATION SELECTOR-24
147 'VS25' => 0xE0108, # VARIATION SELECTOR-25
148 'VS26' => 0xE0109, # VARIATION SELECTOR-26
149 'VS27' => 0xE010A, # VARIATION SELECTOR-27
150 'VS28' => 0xE010B, # VARIATION SELECTOR-28
151 'VS29' => 0xE010C, # VARIATION SELECTOR-29
152 'VS30' => 0xE010D, # VARIATION SELECTOR-30
153 'VS31' => 0xE010E, # VARIATION SELECTOR-31
154 'VS32' => 0xE010F, # VARIATION SELECTOR-32
155 'VS33' => 0xE0110, # VARIATION SELECTOR-33
156 'VS34' => 0xE0111, # VARIATION SELECTOR-34
157 'VS35' => 0xE0112, # VARIATION SELECTOR-35
158 'VS36' => 0xE0113, # VARIATION SELECTOR-36
159 'VS37' => 0xE0114, # VARIATION SELECTOR-37
160 'VS38' => 0xE0115, # VARIATION SELECTOR-38
161 'VS39' => 0xE0116, # VARIATION SELECTOR-39
162 'VS40' => 0xE0117, # VARIATION SELECTOR-40
163 'VS41' => 0xE0118, # VARIATION SELECTOR-41
164 'VS42' => 0xE0119, # VARIATION SELECTOR-42
165 'VS43' => 0xE011A, # VARIATION SELECTOR-43
166 'VS44' => 0xE011B, # VARIATION SELECTOR-44
167 'VS45' => 0xE011C, # VARIATION SELECTOR-45
168 'VS46' => 0xE011D, # VARIATION SELECTOR-46
169 'VS47' => 0xE011E, # VARIATION SELECTOR-47
170 'VS48' => 0xE011F, # VARIATION SELECTOR-48
171 'VS49' => 0xE0120, # VARIATION SELECTOR-49
172 'VS50' => 0xE0121, # VARIATION SELECTOR-50
173 'VS51' => 0xE0122, # VARIATION SELECTOR-51
174 'VS52' => 0xE0123, # VARIATION SELECTOR-52
175 'VS53' => 0xE0124, # VARIATION SELECTOR-53
176 'VS54' => 0xE0125, # VARIATION SELECTOR-54
177 'VS55' => 0xE0126, # VARIATION SELECTOR-55
178 'VS56' => 0xE0127, # VARIATION SELECTOR-56
179 'VS57' => 0xE0128, # VARIATION SELECTOR-57
180 'VS58' => 0xE0129, # VARIATION SELECTOR-58
181 'VS59' => 0xE012A, # VARIATION SELECTOR-59
182 'VS60' => 0xE012B, # VARIATION SELECTOR-60
183 'VS61' => 0xE012C, # VARIATION SELECTOR-61
184 'VS62' => 0xE012D, # VARIATION SELECTOR-62
185 'VS63' => 0xE012E, # VARIATION SELECTOR-63
186 'VS64' => 0xE012F, # VARIATION SELECTOR-64
187 'VS65' => 0xE0130, # VARIATION SELECTOR-65
188 'VS66' => 0xE0131, # VARIATION SELECTOR-66
189 'VS67' => 0xE0132, # VARIATION SELECTOR-67
190 'VS68' => 0xE0133, # VARIATION SELECTOR-68
191 'VS69' => 0xE0134, # VARIATION SELECTOR-69
192 'VS70' => 0xE0135, # VARIATION SELECTOR-70
193 'VS71' => 0xE0136, # VARIATION SELECTOR-71
194 'VS72' => 0xE0137, # VARIATION SELECTOR-72
195 'VS73' => 0xE0138, # VARIATION SELECTOR-73
196 'VS74' => 0xE0139, # VARIATION SELECTOR-74
197 'VS75' => 0xE013A, # VARIATION SELECTOR-75
198 'VS76' => 0xE013B, # VARIATION SELECTOR-76
199 'VS77' => 0xE013C, # VARIATION SELECTOR-77
200 'VS78' => 0xE013D, # VARIATION SELECTOR-78
201 'VS79' => 0xE013E, # VARIATION SELECTOR-79
202 'VS80' => 0xE013F, # VARIATION SELECTOR-80
203 'VS81' => 0xE0140, # VARIATION SELECTOR-81
204 'VS82' => 0xE0141, # VARIATION SELECTOR-82
205 'VS83' => 0xE0142, # VARIATION SELECTOR-83
206 'VS84' => 0xE0143, # VARIATION SELECTOR-84
207 'VS85' => 0xE0144, # VARIATION SELECTOR-85
208 'VS86' => 0xE0145, # VARIATION SELECTOR-86
209 'VS87' => 0xE0146, # VARIATION SELECTOR-87
210 'VS88' => 0xE0147, # VARIATION SELECTOR-88
211 'VS89' => 0xE0148, # VARIATION SELECTOR-89
212 'VS90' => 0xE0149, # VARIATION SELECTOR-90
213 'VS91' => 0xE014A, # VARIATION SELECTOR-91
214 'VS92' => 0xE014B, # VARIATION SELECTOR-92
215 'VS93' => 0xE014C, # VARIATION SELECTOR-93
216 'VS94' => 0xE014D, # VARIATION SELECTOR-94
217 'VS95' => 0xE014E, # VARIATION SELECTOR-95
218 'VS96' => 0xE014F, # VARIATION SELECTOR-96
219 'VS97' => 0xE0150, # VARIATION SELECTOR-97
220 'VS98' => 0xE0151, # VARIATION SELECTOR-98
221 'VS99' => 0xE0152, # VARIATION SELECTOR-99
222 'VS100' => 0xE0153, # VARIATION SELECTOR-100
223 'VS101' => 0xE0154, # VARIATION SELECTOR-101
224 'VS102' => 0xE0155, # VARIATION SELECTOR-102
225 'VS103' => 0xE0156, # VARIATION SELECTOR-103
226 'VS104' => 0xE0157, # VARIATION SELECTOR-104
227 'VS105' => 0xE0158, # VARIATION SELECTOR-105
228 'VS106' => 0xE0159, # VARIATION SELECTOR-106
229 'VS107' => 0xE015A, # VARIATION SELECTOR-107
230 'VS108' => 0xE015B, # VARIATION SELECTOR-108
231 'VS109' => 0xE015C, # VARIATION SELECTOR-109
232 'VS110' => 0xE015D, # VARIATION SELECTOR-110
233 'VS111' => 0xE015E, # VARIATION SELECTOR-111
234 'VS112' => 0xE015F, # VARIATION SELECTOR-112
235 'VS113' => 0xE0160, # VARIATION SELECTOR-113
236 'VS114' => 0xE0161, # VARIATION SELECTOR-114
237 'VS115' => 0xE0162, # VARIATION SELECTOR-115
238 'VS116' => 0xE0163, # VARIATION SELECTOR-116
239 'VS117' => 0xE0164, # VARIATION SELECTOR-117
240 'VS118' => 0xE0165, # VARIATION SELECTOR-118
241 'VS119' => 0xE0166, # VARIATION SELECTOR-119
242 'VS120' => 0xE0167, # VARIATION SELECTOR-120
243 'VS121' => 0xE0168, # VARIATION SELECTOR-121
244 'VS122' => 0xE0169, # VARIATION SELECTOR-122
245 'VS123' => 0xE016A, # VARIATION SELECTOR-123
246 'VS124' => 0xE016B, # VARIATION SELECTOR-124
247 'VS125' => 0xE016C, # VARIATION SELECTOR-125
248 'VS126' => 0xE016D, # VARIATION SELECTOR-126
249 'VS127' => 0xE016E, # VARIATION SELECTOR-127
250 'VS128' => 0xE016F, # VARIATION SELECTOR-128
251 'VS129' => 0xE0170, # VARIATION SELECTOR-129
252 'VS130' => 0xE0171, # VARIATION SELECTOR-130
253 'VS131' => 0xE0172, # VARIATION SELECTOR-131
254 'VS132' => 0xE0173, # VARIATION SELECTOR-132
255 'VS133' => 0xE0174, # VARIATION SELECTOR-133
256 'VS134' => 0xE0175, # VARIATION SELECTOR-134
257 'VS135' => 0xE0176, # VARIATION SELECTOR-135
258 'VS136' => 0xE0177, # VARIATION SELECTOR-136
259 'VS137' => 0xE0178, # VARIATION SELECTOR-137
260 'VS138' => 0xE0179, # VARIATION SELECTOR-138
261 'VS139' => 0xE017A, # VARIATION SELECTOR-139
262 'VS140' => 0xE017B, # VARIATION SELECTOR-140
263 'VS141' => 0xE017C, # VARIATION SELECTOR-141
264 'VS142' => 0xE017D, # VARIATION SELECTOR-142
265 'VS143' => 0xE017E, # VARIATION SELECTOR-143
266 'VS144' => 0xE017F, # VARIATION SELECTOR-144
267 'VS145' => 0xE0180, # VARIATION SELECTOR-145
268 'VS146' => 0xE0181, # VARIATION SELECTOR-146
269 'VS147' => 0xE0182, # VARIATION SELECTOR-147
270 'VS148' => 0xE0183, # VARIATION SELECTOR-148
271 'VS149' => 0xE0184, # VARIATION SELECTOR-149
272 'VS150' => 0xE0185, # VARIATION SELECTOR-150
273 'VS151' => 0xE0186, # VARIATION SELECTOR-151
274 'VS152' => 0xE0187, # VARIATION SELECTOR-152
275 'VS153' => 0xE0188, # VARIATION SELECTOR-153
276 'VS154' => 0xE0189, # VARIATION SELECTOR-154
277 'VS155' => 0xE018A, # VARIATION SELECTOR-155
278 'VS156' => 0xE018B, # VARIATION SELECTOR-156
279 'VS157' => 0xE018C, # VARIATION SELECTOR-157
280 'VS158' => 0xE018D, # VARIATION SELECTOR-158
281 'VS159' => 0xE018E, # VARIATION SELECTOR-159
282 'VS160' => 0xE018F, # VARIATION SELECTOR-160
283 'VS161' => 0xE0190, # VARIATION SELECTOR-161
284 'VS162' => 0xE0191, # VARIATION SELECTOR-162
285 'VS163' => 0xE0192, # VARIATION SELECTOR-163
286 'VS164' => 0xE0193, # VARIATION SELECTOR-164
287 'VS165' => 0xE0194, # VARIATION SELECTOR-165
288 'VS166' => 0xE0195, # VARIATION SELECTOR-166
289 'VS167' => 0xE0196, # VARIATION SELECTOR-167
290 'VS168' => 0xE0197, # VARIATION SELECTOR-168
291 'VS169' => 0xE0198, # VARIATION SELECTOR-169
292 'VS170' => 0xE0199, # VARIATION SELECTOR-170
293 'VS171' => 0xE019A, # VARIATION SELECTOR-171
294 'VS172' => 0xE019B, # VARIATION SELECTOR-172
295 'VS173' => 0xE019C, # VARIATION SELECTOR-173
296 'VS174' => 0xE019D, # VARIATION SELECTOR-174
297 'VS175' => 0xE019E, # VARIATION SELECTOR-175
298 'VS176' => 0xE019F, # VARIATION SELECTOR-176
299 'VS177' => 0xE01A0, # VARIATION SELECTOR-177
300 'VS178' => 0xE01A1, # VARIATION SELECTOR-178
301 'VS179' => 0xE01A2, # VARIATION SELECTOR-179
302 'VS180' => 0xE01A3, # VARIATION SELECTOR-180
303 'VS181' => 0xE01A4, # VARIATION SELECTOR-181
304 'VS182' => 0xE01A5, # VARIATION SELECTOR-182
305 'VS183' => 0xE01A6, # VARIATION SELECTOR-183
306 'VS184' => 0xE01A7, # VARIATION SELECTOR-184
307 'VS185' => 0xE01A8, # VARIATION SELECTOR-185
308 'VS186' => 0xE01A9, # VARIATION SELECTOR-186
309 'VS187' => 0xE01AA, # VARIATION SELECTOR-187
310 'VS188' => 0xE01AB, # VARIATION SELECTOR-188
311 'VS189' => 0xE01AC, # VARIATION SELECTOR-189
312 'VS190' => 0xE01AD, # VARIATION SELECTOR-190
313 'VS191' => 0xE01AE, # VARIATION SELECTOR-191
314 'VS192' => 0xE01AF, # VARIATION SELECTOR-192
315 'VS193' => 0xE01B0, # VARIATION SELECTOR-193
316 'VS194' => 0xE01B1, # VARIATION SELECTOR-194
317 'VS195' => 0xE01B2, # VARIATION SELECTOR-195
318 'VS196' => 0xE01B3, # VARIATION SELECTOR-196
319 'VS197' => 0xE01B4, # VARIATION SELECTOR-197
320 'VS198' => 0xE01B5, # VARIATION SELECTOR-198
321 'VS199' => 0xE01B6, # VARIATION SELECTOR-199
322 'VS200' => 0xE01B7, # VARIATION SELECTOR-200
323 'VS201' => 0xE01B8, # VARIATION SELECTOR-201
324 'VS202' => 0xE01B9, # VARIATION SELECTOR-202
325 'VS203' => 0xE01BA, # VARIATION SELECTOR-203
326 'VS204' => 0xE01BB, # VARIATION SELECTOR-204
327 'VS205' => 0xE01BC, # VARIATION SELECTOR-205
328 'VS206' => 0xE01BD, # VARIATION SELECTOR-206
329 'VS207' => 0xE01BE, # VARIATION SELECTOR-207
330 'VS208' => 0xE01BF, # VARIATION SELECTOR-208
331 'VS209' => 0xE01C0, # VARIATION SELECTOR-209
332 'VS210' => 0xE01C1, # VARIATION SELECTOR-210
333 'VS211' => 0xE01C2, # VARIATION SELECTOR-211
334 'VS212' => 0xE01C3, # VARIATION SELECTOR-212
335 'VS213' => 0xE01C4, # VARIATION SELECTOR-213
336 'VS214' => 0xE01C5, # VARIATION SELECTOR-214
337 'VS215' => 0xE01C6, # VARIATION SELECTOR-215
338 'VS216' => 0xE01C7, # VARIATION SELECTOR-216
339 'VS217' => 0xE01C8, # VARIATION SELECTOR-217
340 'VS218' => 0xE01C9, # VARIATION SELECTOR-218
341 'VS219' => 0xE01CA, # VARIATION SELECTOR-219
342 'VS220' => 0xE01CB, # VARIATION SELECTOR-220
343 'VS221' => 0xE01CC, # VARIATION SELECTOR-221
344 'VS222' => 0xE01CD, # VARIATION SELECTOR-222
345 'VS223' => 0xE01CE, # VARIATION SELECTOR-223
346 'VS224' => 0xE01CF, # VARIATION SELECTOR-224
347 'VS225' => 0xE01D0, # VARIATION SELECTOR-225
348 'VS226' => 0xE01D1, # VARIATION SELECTOR-226
349 'VS227' => 0xE01D2, # VARIATION SELECTOR-227
350 'VS228' => 0xE01D3, # VARIATION SELECTOR-228
351 'VS229' => 0xE01D4, # VARIATION SELECTOR-229
352 'VS230' => 0xE01D5, # VARIATION SELECTOR-230
353 'VS231' => 0xE01D6, # VARIATION SELECTOR-231
354 'VS232' => 0xE01D7, # VARIATION SELECTOR-232
355 'VS233' => 0xE01D8, # VARIATION SELECTOR-233
356 'VS234' => 0xE01D9, # VARIATION SELECTOR-234
357 'VS235' => 0xE01DA, # VARIATION SELECTOR-235
358 'VS236' => 0xE01DB, # VARIATION SELECTOR-236
359 'VS237' => 0xE01DC, # VARIATION SELECTOR-237
360 'VS238' => 0xE01DD, # VARIATION SELECTOR-238
361 'VS239' => 0xE01DE, # VARIATION SELECTOR-239
362 'VS240' => 0xE01DF, # VARIATION SELECTOR-240
363 'VS241' => 0xE01E0, # VARIATION SELECTOR-241
364 'VS242' => 0xE01E1, # VARIATION SELECTOR-242
365 'VS243' => 0xE01E2, # VARIATION SELECTOR-243
366 'VS244' => 0xE01E3, # VARIATION SELECTOR-244
367 'VS245' => 0xE01E4, # VARIATION SELECTOR-245
368 'VS246' => 0xE01E5, # VARIATION SELECTOR-246
369 'VS247' => 0xE01E6, # VARIATION SELECTOR-247
370 'VS248' => 0xE01E7, # VARIATION SELECTOR-248
371 'VS249' => 0xE01E8, # VARIATION SELECTOR-249
372 'VS250' => 0xE01E9, # VARIATION SELECTOR-250
373 'VS251' => 0xE01EA, # VARIATION SELECTOR-251
374 'VS252' => 0xE01EB, # VARIATION SELECTOR-252
375 'VS253' => 0xE01EC, # VARIATION SELECTOR-253
376 'VS254' => 0xE01ED, # VARIATION SELECTOR-254
377 'VS255' => 0xE01EE, # VARIATION SELECTOR-255
378 'VS256' => 0xE01EF, # VARIATION SELECTOR-256
379 'WJ' => 0x2060, # WORD JOINER
380 'ZWJ' => 0x200D, # ZERO WIDTH JOINER
381 'ZWNJ' => 0x200C, # ZERO WIDTH NON-JOINER
382 'ZWSP' => 0x200B, # ZERO WIDTH SPACE
385 my %deprecated_aliases = (
386 # Pre-3.2 compatibility (only for the first 256 characters).
387 # Use of these gives deprecated message.
388 'HORIZONTAL TABULATION' => 0x09, # CHARACTER TABULATION
389 'VERTICAL TABULATION' => 0x0B, # LINE TABULATION
390 'FILE SEPARATOR' => 0x1C, # INFORMATION SEPARATOR FOUR
391 'GROUP SEPARATOR' => 0x1D, # INFORMATION SEPARATOR THREE
392 'RECORD SEPARATOR' => 0x1E, # INFORMATION SEPARATOR TWO
393 'UNIT SEPARATOR' => 0x1F, # INFORMATION SEPARATOR ONE
394 'HORIZONTAL TABULATION SET' => 0x88, # CHARACTER TABULATION SET
395 'HORIZONTAL TABULATION WITH JUSTIFICATION' => 0x89, # CHARACTER TABULATION WITH JUSTIFICATION
396 'PARTIAL LINE DOWN' => 0x8B, # PARTIAL LINE FORWARD
397 'PARTIAL LINE UP' => 0x8C, # PARTIAL LINE BACKWARD
398 'VERTICAL TABULATION SET' => 0x8A, # LINE TABULATION SET
399 'REVERSE INDEX' => 0x8D, # REVERSE LINE FEED
403 my $txt; # The table of official character names
405 my %full_names_cache; # Holds already-looked-up names, so don't have to
406 # re-look them up again. The previous versions of charnames had scoping
407 # bugs. For example if we use script A in one scope and find and cache
408 # what Z resolves to, we can't use that cache in a different scope that
409 # uses script B instead of A, as Z might be an entirely different letter
410 # there; or there might be different aliases in effect in different
411 # scopes, or :short may be in effect or not effect in different scopes,
412 # or various combinations thereof. This was solved in this version
413 # mostly by moving things to %^H. But some things couldn't be moved
414 # there. One of them was the cache of runtime looked-up names, in part
415 # because %^H is read-only at runtime. I (khw) don't know why the cache
416 # was run-time only in the previous versions: perhaps oversight; perhaps
417 # that compile time looking doesn't happen in a loop so didn't think it
418 # was worthwhile; perhaps not wanting to make the cache too large. But
419 # I decided to make it compile time as well; this could easily be
421 # Anyway, this hash is not scoped, and is added to at runtime. It
422 # doesn't have scoping problems because the data in it is restricted to
423 # official names, which are always invariant, and we only set it and
424 # look at it at during :full lookups, so is unaffected by any other
425 # scoped options. I put this in to maintain parity with the older
426 # version. If desired, a %short_names cache could also be made, as well
427 # as one for each script, say in %script_names_cache, with each key
428 # being a hash for a script named in a 'use charnames' statement. I
429 # decided not to do that for now, just because it's added complication,
430 # and because I'm just trying to maintain parity, not extend it.
432 # Designed so that test decimal first, and then hex. Leading zeros
433 # imply non-decimal, as do non-[0-9]
434 my $decimal_qr = qr/^[1-9]\d*$/;
436 # Returns the hex number in $1.
437 my $hex_qr = qr/^(?:[Uu]\+|0[xX])?([[:xdigit:]]+)$/;
441 require Carp; goto &Carp::croak;
446 require Carp; goto &Carp::carp;
449 sub alias (@) # Set up a single alias
451 my $alias = ref $_[0] ? $_[0] : { @_ };
452 foreach my $name (keys %$alias) {
453 my $value = $alias->{$name};
454 next unless defined $value; # Omit if screwed up.
456 # Is slightly slower to just after this statement see if it is
457 # decimal, since we already know it is after having converted from
458 # hex, but makes the code easier to maintain, and is called
459 # infrequently, only at compile-time
460 if ($value !~ $decimal_qr && $value =~ $hex_qr) {
461 $value = CORE::hex $1;
463 if ($value =~ $decimal_qr) {
464 $^H{charnames_ord_aliases}{$name} = $value;
466 # Use a canonical form.
467 $^H{charnames_inverse_ords}{sprintf("%04X", $value)} = $name;
470 # XXX validate syntax when deprecation cycle complete. ie. start
471 # with an alpha only, etc.
472 $^H{charnames_name_aliases}{$name} = $value;
477 sub not_legal_use_bytes_msg {
478 my ($name, $ord) = @_;
479 return sprintf("Character 0x%04x with name '$name' is above 0xFF with 'use bytes' in effect", $ord);
482 sub alias_file ($) # Reads a file containing alias definitions
484 my ($arg, $file) = @_;
485 if (-f $arg && File::Spec->file_name_is_absolute ($arg)) {
488 elsif ($arg =~ m/^\w+$/) {
489 $file = "unicore/${arg}_alias.pl";
492 croak "Charnames alias files can only have identifier characters";
494 if (my @alias = do $file) {
495 @alias == 1 && !defined $alias[0] and
496 croak "$file cannot be used as alias file for charnames";
498 croak "$file did not return a (valid) list of alias pairs";
505 # For use when don't import anything. This structure must be kept in
506 # sync with the one that import() fills up.
508 charnames_stringified_names => "",
509 charnames_stringified_ords => "",
510 charnames_scripts => "",
512 charnames_short => 0,
516 sub lookup_name ($;$) {
518 # Finds the ordinal of a character name, first in the aliases, then in
519 # the large table. If not found, returns undef if runtime; if
520 # compile, complains and returns the Unicode replacement character.
522 my $runtime = (@_ > 1); # compile vs run time
524 my ($name, $hints_ref) = @_;
531 # If we didn't import anything (which happens with 'use charnames ()',
532 # substitute a dummy structure.
533 $hints_ref = \%dummy_H if ! defined $hints_ref
534 || ! defined $hints_ref->{charnames_full};
536 # At runtime, but currently not at compile time, $^H gets
537 # stringified, so un-stringify back to the original data structures.
538 # These get thrown away by perl before the next invocation
539 # Also fill in the hash with the non-stringified data.
540 # N.B. New fields must be also added to %dummy_H
542 %{$^H{charnames_name_aliases}} = split ',',
543 $hints_ref->{charnames_stringified_names};
544 %{$^H{charnames_ord_aliases}} = split ',',
545 $hints_ref->{charnames_stringified_ords};
546 $^H{charnames_scripts} = $hints_ref->{charnames_scripts};
547 $^H{charnames_full} = $hints_ref->{charnames_full};
548 $^H{charnames_short} = $hints_ref->{charnames_short};
551 # User alias should be checked first or else can't override ours, and if we
552 # add any, could conflict with theirs.
553 if (exists $^H{charnames_ord_aliases}{$name}) {
554 $ord = $^H{charnames_ord_aliases}{$name};
556 elsif (exists $^H{charnames_name_aliases}{$name}) {
557 $name = $^H{charnames_name_aliases}{$name};
558 $save_input = $name; # Cache the result for any error message
560 elsif (exists $system_aliases{$name}) {
561 $ord = $system_aliases{$name};
563 elsif (exists $deprecated_aliases{$name}) {
565 warnings::warnif('deprecated', "Unicode character name \"$name\" is deprecated, use \"" . viacode($deprecated_aliases{$name}) . "\" instead");
566 $ord = $deprecated_aliases{$name};
571 if (! defined $ord) {
573 # See if has looked this up earlier.
574 if ($^H{charnames_full} && exists $full_names_cache{$name}) {
575 $ord = $full_names_cache{$name};
579 ## Suck in the code/name list as a big string.
581 ## "0052\t\tLATIN CAPITAL LETTER R\n"
582 $txt = do "unicore/Name.pl" unless $txt;
584 ## @off will hold the index into the code/name string of the start and
585 ## end of the name as we find it.
587 ## If :full, look for the name exactly; runtime implies full
588 my $found_full_in_table = 0; # Tells us if can cache the result
589 if ($^H{charnames_full}) {
591 # See if the name is one which is algorithmically determinable.
592 # The subroutine is included in Name.pl. The table contained in
593 # $txt doesn't contain these. Experiments show that checking
594 # for these before checking for the regular names has no
595 # noticeable impact on performance for the regular names, but
596 # the other way around slows down finding these immensely.
597 # Algorithmically determinables are not placed in the cache (that
598 # $found_full_in_table indicates) because that uses up memory,
599 # and finding these again is fast.
600 if (! defined ($ord = name_to_code_point_special($name))) {
602 # Not algorthmically determinable; look up in the table.
603 if ($txt =~ /\t\t\Q$name\E$/m) {
604 @off = ($-[0] + 2, $+[0]); # The 2 is for the 2 tabs
605 $found_full_in_table = 1;
610 # If we didn't get it above, keep looking
611 if (! $found_full_in_table && ! defined $ord) {
613 # If :short is allowed, see if input is like "greek:Sigma".
615 if (($^H{charnames_short})
616 && $name =~ /^ \s* (.+?) \s* : \s* (.+?) \s* $ /xs)
618 $scripts_trie = "\U\Q$1";
622 $scripts_trie = $^H{charnames_scripts};
625 my $case = $name =~ /[[:upper:]]/ ? "CAPITAL" : "SMALL";
627 /\t\t (?: $scripts_trie ) \ (?:$case\ )? LETTER \ \U\Q$name\E $/xm)
629 # Here we still don't have it, give up.
632 # May have zapped input name, get it again.
633 $name = (defined $save_input) ? $save_input : $_[0];
634 carp "Unknown charname '$name'";
638 @off = ($-[0] + 2, $+[0]);
641 if (! defined $ord) {
643 ## Now know where in the string the name starts.
644 ## The code, in hex, is before that.
646 ## The code can be 4-6 characters long, so we've got to sort of
647 ## go look for it, just after the newline that comes before $off[0].
649 ## This would be much easier if unicore/Name.pl had info in
650 ## a name/code order, instead of code/name order.
652 ## The +1 after the rindex() is to skip past the newline we're finding,
653 ## or, if the rindex() fails, to put us to an offset of zero.
655 my $hexstart = rindex($txt, "\n", $off[0]) + 1;
657 ## we know where it starts, so turn into number -
658 ## the ordinal for the char.
659 $ord = CORE::hex substr($txt, $hexstart, $off[0] - 2 - $hexstart);
662 # Cache the input so as to not have to search the large table
663 # again, but only if it came from the one search that we cache.
664 $full_names_cache{$name} = $ord if $found_full_in_table;
668 return $ord if $runtime || $ord <= 255 || ! ($^H & $bytes::hint_bits);
670 # Here is compile time, "use bytes" is in effect, and the character
671 # won't fit in a byte
672 # Prefer any official name over the input one.
674 $name = substr($txt, $off[0], $off[1] - $off[0]) if @off;
677 $name = (defined $save_input) ? $save_input : $_[0];
679 croak not_legal_use_bytes_msg($name, $ord);
685 # For \N{...}. Looks up the character name and returns its ordinal if
686 # found, undef otherwise. If not in 'use bytes', forces into utf8
688 my $ord = lookup_name($name);
689 return if ! defined $ord;
690 return chr $ord if $^H & $bytes::hint_bits;
692 no warnings 'utf8'; # allow even illegal characters
693 return pack "U", $ord;
698 shift; ## ignore class name
701 carp("`use charnames' needs explicit imports list");
703 $^H{charnames} = \&charnames ;
704 $^H{charnames_ord_aliases} = {};
705 $^H{charnames_name_aliases} = {};
706 $^H{charnames_inverse_ords} = {};
707 # New fields must be added to %dummy_H, and the code in lookup_name()
708 # that copies fields from the runtime structure
711 ## fill %h keys with our @_ args.
713 my ($promote, %h, @args) = (0);
714 while (my $arg = shift) {
715 if ($arg eq ":alias") {
717 croak ":alias needs an argument in charnames";
720 ref $alias eq "HASH" or
721 croak "Only HASH reference supported as argument to :alias";
725 if ($alias =~ m{:(\w+)$}) {
726 $1 eq "full" || $1 eq "short" and
727 croak ":alias cannot use existing pragma :$1 (reversed order?)";
728 alias_file ($1) and $promote = 1;
734 if (substr($arg, 0, 1) eq ':' and ! ($arg eq ":full" || $arg eq ":short")) {
735 warn "unsupported special '$arg' in charnames";
740 @args == 0 && $promote and @args = (":full");
741 @h{@args} = (1) x @args;
743 $^H{charnames_full} = delete $h{':full'} || 0; # Don't leave undefined,
746 $^H{charnames_short} = delete $h{':short'} || 0;
747 my @scripts = map uc, keys %h;
750 ## If utf8? warnings are enabled, and some scripts were given,
751 ## see if at least we can find one letter from each script.
753 if (warnings::enabled('utf8') && @scripts) {
754 $txt = do "unicore/Name.pl" unless $txt;
756 for my $script (@scripts) {
757 if (not $txt =~ m/\t\t$script (?:CAPITAL |SMALL )?LETTER /) {
758 warnings::warn('utf8', "No such script: '$script'");
759 $script = quotemeta $script; # Escape it, for use in the re.
764 # %^H gets stringified, so serialize it ourselves so can extract the
765 # real data back later.
766 $^H{charnames_stringified_ords} = join ",", %{$^H{charnames_ord_aliases}};
767 $^H{charnames_stringified_names} = join ",", %{$^H{charnames_name_aliases}};
768 $^H{charnames_stringified_inverse_ords} = join ",", %{$^H{charnames_inverse_ords}};
769 $^H{charnames_scripts} = join "|", @scripts; # Stringifiy them as a trie
772 # Cache of already looked-up values. This is set to only contain
773 # official values, and user aliases can't override them, so scoping is
779 # Returns the name of the code point argument
782 carp "charnames::viacode() expects one argument";
788 # This is derived from Unicode::UCD, where it is nearly the same as the
789 # function _getcode(), but here it makes sure that even a hex argument
790 # has the proper number of leading zeros, which is critical in
791 # matching against $txt below
792 # Must check if decimal first; see comments at that definition
794 if ($arg =~ $decimal_qr) {
795 $hex = sprintf "%04X", $arg;
796 } elsif ($arg =~ $hex_qr) {
797 # Below is the line that differs from the _getcode() source
798 $hex = sprintf "%04X", hex $1;
800 carp("unexpected arg \"$arg\" to charnames::viacode()");
804 return $viacode{$hex} if exists $viacode{$hex};
806 # If the code point is above the max in the table, there's no point
807 # looking through it. Checking the length first is slightly faster
808 if (length($hex) <= 5 || CORE::hex($hex) <= 0x10FFFF) {
809 $txt = do "unicore/Name.pl" unless $txt;
811 # See if the name is algorithmically determinable.
812 my $algorithmic = code_point_to_name_special(CORE::hex $hex);
813 if (defined $algorithmic) {
814 $viacode{$hex} = $algorithmic;
818 # Return the official name, if exists. It's unclear to me (khw) at
819 # this juncture if it is better to return a user-defined override, so
820 # leaving it as is for now.
821 if ($txt =~ m/^$hex\t\t/m) {
823 # The name starts with the next character and goes up to the
824 # next new-line. Using capturing parentheses above instead of
825 # @+ more than doubles the execution time in Perl 5.13
826 $viacode{$hex} = substr($txt, $+[0], index($txt, "\n", $+[0]) - $+[0]);
827 return $viacode{$hex};
831 # See if there is a user name for it, before giving up completely.
832 # First get the scoped aliases, give up if have none.
833 my $H_ref = (caller(0))[10];
834 return if ! defined $H_ref
835 || ! exists $H_ref->{charnames_stringified_inverse_ords};
837 my %code_point_aliases = split ',',
838 $H_ref->{charnames_stringified_inverse_ords};
839 if (! exists $code_point_aliases{$hex}) {
840 if (CORE::hex($hex) > 0x10FFFF) {
841 carp "Unicode characters only allocated up to U+10FFFF (you asked for U+$hex)";
846 return $code_point_aliases{$hex};
852 carp "charnames::vianame() expects one name argument";
856 # Looks up the character name and returns its ordinal if
857 # found, undef otherwise.
861 if ($arg =~ /^U\+([0-9a-fA-F]+)$/) {
863 # khw claims that this is bad. The function should return either a
864 # an ord or a chr for all inputs; not be bipolar.
865 my $ord = CORE::hex $1;
866 return chr $ord if $ord <= 255 || ! ((caller 0)[8] & $bytes::hint_bits);
867 carp not_legal_use_bytes_msg($arg, $ord);
871 return lookup_name($arg, (caller(0))[10]);
880 charnames - access to Unicode character names; define character names for C<\N{named}> string literal escapes
884 use charnames ':full';
885 print "\N{GREEK SMALL LETTER SIGMA} is called sigma.\n";
887 use charnames ':short';
888 print "\N{greek:Sigma} is an upper-case sigma.\n";
890 use charnames qw(cyrillic greek);
891 print "\N{sigma} is Greek sigma, and \N{be} is Cyrillic b.\n";
893 use charnames ":full", ":alias" => {
894 e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
895 mychar => 0xE8000, # Private use area
897 print "\N{e_ACUTE} is a small letter e with an acute.\n";
898 print "\\N{mychar} allows me to name private use characters.\n";
901 print charnames::viacode(0x1234); # prints "ETHIOPIC SYLLABLE SEE"
902 printf "%04X", charnames::vianame("GOTHIC LETTER AHSA"); # prints
907 Pragma C<use charnames> is used to gain access to the names of the
908 Unicode characters, and to allow you to define your own character names.
910 All forms of the pragma enable use of the
911 L</charnames::vianame(I<name>)> function for run-time lookup of a
912 character name to get its ordinal (code point), and the inverse
913 function, L</charnames::viacode(I<code>)>.
915 Forms other than C<S<"use charnames ();">> enable the use of of
916 C<\N{I<CHARNAME>}> sequences to compile a Unicode character into a
917 string based on its name.
919 Note that C<\N{U+I<...>}>, where the I<...> is a hexadecimal number,
920 also inserts a character into a string, but doesn't require the use of
921 this pragma. The character it inserts is the one whose code point
922 (ordinal value) is equal to the number. For example, C<"\N{U+263a}"> is
923 the Unicode (white background, black foreground) smiley face; it doesn't
924 require this pragma, whereas the equivalent, C<"\N{WHITE SMILING FACE}">
926 Also, C<\N{I<...>}> can mean a regex quantifier instead of a character
927 name, when the I<...> is a number (or comma separated pair of numbers;
928 see L<perlreref/QUANTIFIERS>), and is not related to this pragma.
930 The C<charnames> pragma supports arguments C<:full>, C<:short>, script
931 names and customized aliases. If C<:full> is present, for expansion of
932 C<\N{I<CHARNAME>}>, the string I<CHARNAME> is first looked up in the list of
933 standard Unicode character names. If C<:short> is present, and
934 I<CHARNAME> has the form C<I<SCRIPT>:I<CNAME>>, then I<CNAME> is looked up
935 as a letter in script I<SCRIPT>. If C<use charnames> is used
936 with script name arguments, then for C<\N{I<CHARNAME>}> the name
937 I<CHARNAME> is looked up as a letter in the given scripts (in the
938 specified order). Customized aliases can override these, and are explained in
941 For lookup of I<CHARNAME> inside a given script I<SCRIPTNAME>
942 this pragma looks for the names
944 SCRIPTNAME CAPITAL LETTER CHARNAME
945 SCRIPTNAME SMALL LETTER CHARNAME
946 SCRIPTNAME LETTER CHARNAME
948 in the table of standard Unicode names. If I<CHARNAME> is lowercase,
949 then the C<CAPITAL> variant is ignored, otherwise the C<SMALL> variant
952 Note that C<\N{...}> is compile-time; it's a special form of string
953 constant used inside double-quotish strings; this means that you cannot
954 use variables inside the C<\N{...}>. If you want similar run-time
955 functionality, use L<charnames::vianame()|/charnames::vianame(I<name>)>.
957 For the C0 and C1 control characters (U+0000..U+001F, U+0080..U+009F)
958 there are no official Unicode names but you can use instead the ISO 6429
959 names (LINE FEED, ESCAPE, and so forth, and their abbreviations, LF,
960 ESC, ...). In Unicode 3.2 (as of Perl 5.8) some naming changes took
961 place, and ISO 6429 was updated, see L</ALIASES>.
963 If the input name is unknown, C<\N{NAME}> raises a warning and
964 substitutes the Unicode REPLACEMENT CHARACTER (U+FFFD).
966 It is a fatal error if C<use bytes> is in effect and the input name is
967 that of a character that won't fit into a byte (i.e., whose ordinal is
970 Otherwise, any string that includes a C<\N{I<charname>}> or
971 C<S<\N{U+I<code point>}>> will automatically have Unicode semantics (see
972 L<perlunicode/Byte and Character Semantics>).
976 A few aliases have been defined for convenience: instead of having
977 to use the official names
984 (yes, with parentheses), one can use
995 All the other standard abbreviations for the controls, such as C<ACK> for
996 C<ACKNOWLEDGE> also can be used.
1003 and these abbreviations
1005 Abbreviation Full Name
1007 CGJ COMBINING GRAPHEME JOINER
1008 FVS1 MONGOLIAN FREE VARIATION SELECTOR ONE
1009 FVS2 MONGOLIAN FREE VARIATION SELECTOR TWO
1010 FVS3 MONGOLIAN FREE VARIATION SELECTOR THREE
1011 LRE LEFT-TO-RIGHT EMBEDDING
1012 LRM LEFT-TO-RIGHT MARK
1013 LRO LEFT-TO-RIGHT OVERRIDE
1014 MMSP MEDIUM MATHEMATICAL SPACE
1015 MVS MONGOLIAN VOWEL SEPARATOR
1017 NNBSP NARROW NO-BREAK SPACE
1018 PDF POP DIRECTIONAL FORMATTING
1019 RLE RIGHT-TO-LEFT EMBEDDING
1020 RLM RIGHT-TO-LEFT MARK
1021 RLO RIGHT-TO-LEFT OVERRIDE
1023 VS1 VARIATION SELECTOR-1
1027 VS256 VARIATION SELECTOR-256
1029 ZWJ ZERO WIDTH JOINER
1030 ZWNJ ZERO WIDTH NON-JOINER
1031 ZWSP ZERO WIDTH SPACE
1033 For backward compatibility one can use the old names for
1034 certain C0 and C1 controls
1038 FILE SEPARATOR INFORMATION SEPARATOR FOUR
1039 GROUP SEPARATOR INFORMATION SEPARATOR THREE
1040 HORIZONTAL TABULATION CHARACTER TABULATION
1041 HORIZONTAL TABULATION SET CHARACTER TABULATION SET
1042 HORIZONTAL TABULATION WITH JUSTIFICATION CHARACTER TABULATION
1044 PARTIAL LINE DOWN PARTIAL LINE FORWARD
1045 PARTIAL LINE UP PARTIAL LINE BACKWARD
1046 RECORD SEPARATOR INFORMATION SEPARATOR TWO
1047 REVERSE INDEX REVERSE LINE FEED
1048 UNIT SEPARATOR INFORMATION SEPARATOR ONE
1049 VERTICAL TABULATION LINE TABULATION
1050 VERTICAL TABULATION SET LINE TABULATION SET
1052 but the old names in addition to giving the character
1053 will also give a warning about being deprecated.
1055 And finally, certain published variants are usable, including some for
1056 controls that have no Unicode names:
1060 END OF PROTECTED AREA END OF GUARDED AREA, U+0097
1061 HIGH OCTET PRESET U+0081
1066 PADDING CHARACTER U+0080
1067 PRIVATE USE 1 PRIVATE USE ONE, U+0091
1068 PRIVATE USE 2 PRIVATE USE TWO, U+0092
1070 SINGLE GRAPHIC CHARACTER INTRODUCER U+0099
1071 SINGLE-SHIFT 2 SINGLE SHIFT TWO, U+008E
1072 SINGLE-SHIFT 3 SINGLE SHIFT THREE, U+008F
1073 START OF PROTECTED AREA START OF GUARDED AREA, U+0096
1075 =head1 CUSTOM ALIASES
1077 You can add customized aliases to standard (C<:full>) Unicode naming
1078 conventions. The aliases override any standard definitions, so, if
1079 you're twisted enough, you can change C<"\N{LATIN CAPITAL LETTER A}"> to
1082 Note that an alias should not be something that is a legal curly
1083 brace-enclosed quantifier (see L<perlreref/QUANTIFIERS>). For example
1084 C<\N{123}> means to match 123 non-newline characters, and is not treated as a
1085 charnames alias. Aliases are discouraged from beginning with anything
1086 other than an alphabetic character and from containing anything other
1087 than alphanumerics, spaces, dashes, parentheses, and underscores.
1088 Currently they must be ASCII.
1090 An alias can map to either an official Unicode character name or to a
1091 numeric code point (ordinal). The latter is useful for assigning names
1092 to code points in Unicode private use areas such as U+E800 through
1094 A numeric code point must be a non-negative integer or a string beginning
1095 with C<"U+"> or C<"0x"> with the remainder considered to be a
1096 hexadecimal integer. A literal numeric constant must be unsigned; it
1097 will be interpreted as hex if it has a leading zero or contains
1098 non-decimal hex digits; otherwise it will be interpreted as decimal.
1100 Aliases are added either by the use of anonymous hashes:
1102 use charnames ":alias" => {
1103 e_ACUTE => "LATIN SMALL LETTER E WITH ACUTE",
1106 my $str = "\N{e_ACUTE}";
1108 or by using a file containing aliases:
1110 use charnames ":alias" => "pro";
1112 will try to read C<"unicore/pro_alias.pl"> from the C<@INC> path. This
1113 file should return a list in plain perl:
1116 A_GRAVE => "LATIN CAPITAL LETTER A WITH GRAVE",
1117 A_CIRCUM => "LATIN CAPITAL LETTER A WITH CIRCUMFLEX",
1118 A_DIAERES => "LATIN CAPITAL LETTER A WITH DIAERESIS",
1119 A_TILDE => "LATIN CAPITAL LETTER A WITH TILDE",
1120 A_BREVE => "LATIN CAPITAL LETTER A WITH BREVE",
1121 A_RING => "LATIN CAPITAL LETTER A WITH RING ABOVE",
1122 A_MACRON => "LATIN CAPITAL LETTER A WITH MACRON",
1123 mychar2 => "U+E8001",
1126 Both these methods insert C<":full"> automatically as the first argument (if no
1127 other argument is given), and you can give the C<":full"> explicitly as
1130 use charnames ":full", ":alias" => "pro";
1132 =head1 charnames::viacode(I<code>)
1134 Returns the full name of the character indicated by the numeric code.
1137 print charnames::viacode(0x2722);
1139 prints "FOUR TEARDROP-SPOKED ASTERISK".
1141 The name returned is the official name for the code point, if
1142 available, otherwise your custom alias for it. This means that your
1143 alias will only be returned for code points that don't have an official
1144 Unicode name (nor Unicode version 1 name), such as private use code
1145 points, and the 4 control characters U+0080, U+0081, U+0084, and U+0099.
1146 If you define more than one name for the code point, it is indeterminate
1147 which one will be returned.
1149 The function returns C<undef> if no name is known for the code point.
1150 In Unicode the proper name of these is the empty string, which
1151 C<undef> stringifies to. (If you ask for a code point past the legal
1152 Unicode maximum of U+10FFFF that you haven't assigned an alias to, you
1153 get C<undef> plus a warning.)
1155 The input number must be a non-negative integer or a string beginning
1156 with C<"U+"> or C<"0x"> with the remainder considered to be a
1157 hexadecimal integer. A literal numeric constant must be unsigned; it
1158 will be interpreted as hex if it has a leading zero or contains
1159 non-decimal hex digits; otherwise it will be interpreted as decimal.
1161 Notice that the name returned for of U+FEFF is "ZERO WIDTH NO-BREAK
1162 SPACE", not "BYTE ORDER MARK".
1164 =head1 charnames::vianame(I<name>)
1166 Returns the code point indicated by the name.
1169 printf "%04X", charnames::vianame("FOUR TEARDROP-SPOKED ASTERISK");
1173 C<vianame> takes the identical inputs that C<\N{...}> does under the
1174 L<C<:full> option|/DESCRIPTION> to C<charnames>. In addition, any other
1175 options for the controlling C<"use charnames"> in the same scope apply,
1176 like any L<script list, C<:short> option|/DESCRIPTION>, or L<custom
1177 aliases|/CUSTOM ALIASES> you may have defined.
1179 There are just a few differences. The main one is that under
1180 most (see L</BUGS> for the others) circumstances, vianame returns
1181 an ord, whereas C<\\N{...}> is seamlessly placed as a chr into the
1182 string in which it appears. This leads to a second difference.
1183 Since an ord is returned, it can be that of any character, even one
1184 that isn't legal under the C<S<use bytes>> pragma.
1186 The final difference is that if the input name is unknown C<vianame>
1187 returns C<undef> instead of the REPLACEMENT CHARACTER, and it does not
1188 raise a warning message.
1190 =head1 CUSTOM TRANSLATORS
1192 The mechanism of translation of C<\N{...}> escapes is general and not
1193 hardwired into F<charnames.pm>. A module can install custom
1194 translations (inside the scope which C<use>s the module) with the
1195 following magic incantation:
1199 $^H{charnames} = \&translator;
1202 Here translator() is a subroutine which takes I<CHARNAME> as an
1203 argument, and returns text to insert into the string instead of the
1204 C<\N{I<CHARNAME>}> escape. Since the text to insert should be different
1205 in C<bytes> mode and out of it, the function should check the current
1206 state of C<bytes>-flag as in:
1208 use bytes (); # for $bytes::hint_bits
1210 if ($^H & $bytes::hint_bits) {
1211 return bytes_translator(@_);
1214 return utf8_translator(@_);
1218 See L</CUSTOM ALIASES> above for restrictions on I<CHARNAME>.
1220 Of course, C<vianame> and C<viacode> would need to be overridden as
1225 vianame returns a chr if the input name is of the form C<U+...>, and an ord
1226 otherwise. It is proposed to change this to always return an ord. Send email
1227 to C<perl5-porters@perl.org> to comment on this proposal. If S<C<use
1228 bytes>> is in effect when a chr is returned, and if that chr won't fit
1229 into a byte, C<undef> is returned instead.
1231 Names must be ASCII characters only, which means that you are out of luck if
1232 you want to create aliases in a language where some or all the characters of
1233 the desired aliases are non-ASCII.
1235 Unicode standard named sequences are not recognized, such as
1236 C<LATIN CAPITAL LETTER A WITH MACRON AND GRAVE>
1237 (which should mean C<LATIN CAPITAL LETTER A WITH MACRON> with an additional
1238 C<COMBINING GRAVE ACCENT>).
1240 Since evaluation of the translation function (see L</CUSTOM
1241 TRANSLATORS>) happens in the middle of compilation (of a string
1242 literal), the translation function should not do any C<eval>s or
1243 C<require>s. This restriction should be lifted (but is low priority) in
1244 a future version of Perl.
1248 # ex: set ts=8 sts=2 sw=2 et: